# vercel ai sdk

Open-source TypeScript toolkit for building AI-powered applications and agents with multi-provider model support and streaming UI capabilities.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## How I Traced a Missing Vercel AI SDK Duration Histogram

DevFeed: [How I Traced a Missing Vercel AI SDK Duration Histogram](<https://devfeed.tech/articles/how-i-traced-a-missing-vercel-ai-sdk-duration-histogram-146215.md>)

Original publisher: [Read original article](<https://hackernoon.com/how-i-traced-a-missing-vercel-ai-sdk-duration-histogram?source=rss>)

Author: Aditya Reddy

Published: 2026-11-20T10:15:02Z

Content type: tutorial

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Integration testing](<https://devfeed.tech/topics/integration-testing.md>), [SDK](<https://devfeed.tech/topics/sdk.md>)

Tags: [ai-observability](<https://devfeed.tech/tags/ai-observability.md>), [ai-sdk-telemetry](<https://devfeed.tech/tags/ai-sdk-telemetry.md>), [distributed-tracing](<https://devfeed.tech/tags/distributed-tracing.md>), [failures](<https://devfeed.tech/tags/failures.md>), [generation](<https://devfeed.tech/tags/generation.md>), [inference](<https://devfeed.tech/tags/inference.md>), [llm-observability](<https://devfeed.tech/tags/llm-observability.md>), [observability](<https://devfeed.tech/tags/observability.md>), [opentelemetry](<https://devfeed.tech/tags/opentelemetry.md>), [performance-monitoring](<https://devfeed.tech/tags/performance-monitoring.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [vercel](<https://devfeed.tech/tags/vercel.md>), [vercel-ai-sdk](<https://devfeed.tech/tags/vercel-ai-sdk.md>)

### AI overview

In the author's controlled comparison, `@ai-sdk/otel` 1.0.157 exported no inference duration histogram, while 1.0.160 recorded 25 observations across generation, streaming, and five thrown errors. A span's `gen_ai.client.operation.duration` attribute did not itself produce a metric: tracing and metrics use separate provider paths, and the histogram requires a `MeterProvider`, reader, and exporter. The author checked the in-memory export against a control counter, flushed after each sequential mock call, and derived per-call durations from cumulative sums. For a stream, the histogram measured the full invocation (median 202.3 ms), while first text arrived at a median 43.6 ms; these are distinct timings. Counts represent model attempts, retries may add attempts, and local tool execution is outside the duration. The comparison used pinned package versions and mock calls; it does not establish behavior for every real service or backend.

### Source excerpt

I ran 25 mock calls per version to see how the Vercel AI SDK records generation, streaming and failures in its OpenTelemetry inference histogram.

## GPT-Live 1.1 now available on AI Gateway

DevFeed: [GPT-Live 1.1 now available on AI Gateway](<https://devfeed.tech/articles/gpt-live-1-1-now-available-on-ai-gateway-144669.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/gpt-live-1-1-now-available-on-ai-gateway>)

Author: Zachary Chen

Published: 2026-11-19T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [OpenAI](<https://devfeed.tech/topics/openai.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [api](<https://devfeed.tech/tags/api.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [application](<https://devfeed.tech/tags/application.md>), [audio](<https://devfeed.tech/tags/audio.md>), [bring-your-own-key](<https://devfeed.tech/tags/bring-your-own-key.md>), [byok](<https://devfeed.tech/tags/byok.md>), [cancellation](<https://devfeed.tech/tags/cancellation.md>), [channel](<https://devfeed.tech/tags/channel.md>), [client](<https://devfeed.tech/tags/client.md>), [commentary](<https://devfeed.tech/tags/commentary.md>), [cost](<https://devfeed.tech/tags/cost.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [delegation](<https://devfeed.tech/tags/delegation.md>), [event](<https://devfeed.tech/tags/event.md>), [failover](<https://devfeed.tech/tags/failover.md>), [gpt-6-2-sol](<https://devfeed.tech/tags/gpt-6-2-sol.md>), [gpt-live](<https://devfeed.tech/tags/gpt-live.md>), [inference](<https://devfeed.tech/tags/inference.md>), [openai](<https://devfeed.tech/tags/openai.md>)

### AI overview

GPT-Live 1.1 is a full-duplex voice model: callers can interrupt or add detail while it speaks. The source says it transcribes more accurately and maintains a more consistent voice and accent across languages than the previous GPT-Live model. Existing integrations can switch by changing the model ID while keeping the Live endpoint. For delegated work, the application enables client delegation, handles the delegation-created event, calls a text model such as openai/gpt-6.2-sol, and returns its result on the commentary channel for GPT-Live to speak. The application controls delegated permissions, confirmations, and cancellation. Delegated requests are billed separately, while voice-session usage continues during them. The example snippets omit connection setup and other streaming and event-handling details.

### Source excerpt

GPT-Live 1.1 from OpenAI is now available on AI Gateway. GPT-Live 1.1 is a full-duplex voice model, so it listens while it speaks and a caller can pause, interrupt, or add detail mid-reply. Compared with the previous GPT-Live model, it transcribes speech more accurately and keeps a more consistent accent and voice across languages. It uses the same Live endpoint and client delegation, so an existing GPT-Live integration only needs the new model ID. Simple example without delegation Run openai/gpt-live-1.1 by itself: Delegate work and keep talking Turn on client delegation, and use the session instructions to tell GPT-Live 1.1 when to ask for help. It asks by sending delegation-created. Answer with any text model on AI Gateway and return the result on the commentary channel for GPT-Live to speak. This example uses openai/gpt-6.2-sol and builds on the session above: Your application controls delegated work and its permissions, confirmations, and cancellation. Delegated model requests are billed separately through AI Gateway, and voice-session usage continues while they run. These snippets omit the WebSocket connection, event parsing, transcript assembly, audio streaming, and shutdown. See the GPT-Live guide for connection setup, audio streaming, and complete examples. Try GPT-Live 1.1 in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all models available on AI Gateway. Read more

## GPT-6.2 Astra and Sol now available on AI Gateway

DevFeed: [GPT-6.2 Astra and Sol now available on AI Gateway](<https://devfeed.tech/articles/gpt-6-2-astra-and-sol-now-available-on-ai-gateway-138550.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/gpt-6-2-astra-and-sol-now-available-on-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-11-17T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [gpt-6-astra](<https://devfeed.tech/topics/gpt-6-astra.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [api](<https://devfeed.tech/tags/api.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [complex](<https://devfeed.tech/tags/complex.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [gpt-6-2](<https://devfeed.tech/tags/gpt-6-2.md>), [gpt-6-2-astra](<https://devfeed.tech/tags/gpt-6-2-astra.md>), [gpt-6-2-sol](<https://devfeed.tech/tags/gpt-6-2-sol.md>), [openai](<https://devfeed.tech/tags/openai.md>), [responses-api](<https://devfeed.tech/tags/responses-api.md>), [web-applications](<https://devfeed.tech/tags/web-applications.md>)

### AI overview

GPT-6.2 Astra and GPT-6.2 Sol are available through AI Gateway. Astra is positioned for complex, multi-step work, with improvements to changing and testing existing code, following document templates, and computer use. Sol targets everyday coding, writing, and agent workflows, including building interactive web apps from a written brief. Use model IDs `openai/gpt-6.2-astra` and `openai/gpt-6.2-sol`; API examples require `AI_GATEWAY_API_KEY`, and both models support the Responses API. Both offer fast mode and OpenAI's Ultrafast tier for lower latency at higher per-token rates, configurable with `providerOptions.openai.serviceTier: 'ultrafast'` in the AI SDK or `service_tier: 'ultrafast'` in Chat Completions and Responses requests. Astra's Ultrafast output-token price is stated to be 60% lower than GPT-6 Astra's. For coding agents such as Codex and Cursor, install the latest Vercel CLI, run `npx vercel ai-gateway setup`, then select a model.

### Source excerpt

GPT-6.2 Astra and GPT-6.2 Sol from OpenAI are now available on AI Gateway. GPT-6.2 Astra: for complex, multi-step projects, with improvements to implementing and testing changes in existing codebases, following document templates, and computer use GPT-6.2 Sol: for everyday coding, writing, and agent workflows, including building interactive web applications from a written brief Use openai/gpt-6.2-astra or openai/gpt-6.2-sol as the model ID. For the API examples, set AI_GATEWAY_API_KEY to your AI Gateway API key. Both models also support the Responses API. For lower latency at higher per-token rates, both models support fast mode and OpenAI's Ultrafast service tier. To request Ultrafast, set providerOptions.openai.serviceTier to 'ultrafast' in the AI SDK, or set service_tier to 'ultrafast' in Chat Completions and Responses requests. GPT-6.2 Astra's Ultrafast output-token price is 60% lower than GPT-6 Astra's. To use the models in coding agents like Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select openai/gpt-6.2-astra or openai/gpt-6.2-sol in the agent. See the coding agents guide for details. Try GPT-6.2 Astra or GPT-6.2 Sol in the playground. Read more

## Hy4 Flash now available on AI Gateway for 50% off

DevFeed: [Hy4 Flash now available on AI Gateway for 50% off](<https://devfeed.tech/articles/hy4-flash-now-available-on-ai-gateway-for-50-off-136002.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/hy4-flash-now-available-on-ai-gateway-for-50-off>)

Author: Jerilyn Zheng

Published: 2026-11-16T17:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [litellm](<https://devfeed.tech/topics/litellm.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [api](<https://devfeed.tech/tags/api.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [bring-your-own-key](<https://devfeed.tech/tags/bring-your-own-key.md>), [byok](<https://devfeed.tech/tags/byok.md>), [caching](<https://devfeed.tech/tags/caching.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [discount](<https://devfeed.tech/tags/discount.md>), [flash](<https://devfeed.tech/tags/flash.md>), [hy4](<https://devfeed.tech/tags/hy4.md>), [tencent](<https://devfeed.tech/tags/tencent.md>)

### AI overview

Tencent's Hy4 Flash is available through AI Gateway at a stated introductory 50% discount on input, cached input, and output tokens through November 29, 2026. The lower-cost Hy4 model retains reasoning across turns, tool calling, structured outputs, prompt caching, image input, and a 1M-token context window; reasoning can be disabled for requests that do not need it. Use model ID `tencent/hy4-flash` in the AI SDK, or install the latest Vercel CLI, run `npx vercel ai-gateway setup`, and select the model in a supported coding agent. AI Gateway offers usage and cost tracking, retries, failover, routing, reporting, Zero Data Retention support, and API-key budgets. It says it applies no markup to provider pricing and charges no inference platform fee, including for BYOK requests.

### Source excerpt

Hy4 Flash from Tencent is now available on AI Gateway with an introductory 50% discount on input, cached input, and output tokens through November 29, 2026. Hy4 Flash is the new lower-cost model in the Hy4 family. It keeps the full Hy4 feature set at roughly a tenth of the price per token: reasoning with preserved thinking across turns, tool calling, structured outputs, prompt caching, and image input, with the same 1M-token context window. Reasoning can be turned off for requests that don't need it, which suits high-volume coding, agent, and document workloads. Use tencent/hy4-flash as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select tencent/hy4-flash in the agent. See the coding agents guide for details. Try Hy4 Flash in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Gemini 4 Carbon now available on AI Gateway

DevFeed: [Gemini 4 Carbon now available on AI Gateway](<https://devfeed.tech/articles/gemini-4-carbon-now-available-on-ai-gateway-126761.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/gemini-4-carbon-now-available-on-ai-gateway>)

Author: Zachary Chen

Published: 2026-11-10T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [api](<https://devfeed.tech/tags/api.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [failover](<https://devfeed.tech/tags/failover.md>), [full-stack](<https://devfeed.tech/tags/full-stack.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [google](<https://devfeed.tech/tags/google.md>), [performance](<https://devfeed.tech/tags/performance.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>)

### AI overview

Google's Gemini 4 Carbon is available through Vercel AI Gateway under the model name `google/gemini-4-carbon`, with 50% off through November 30, 2026. The text describes a 1M-token context window and capabilities for multi-stage software engineering and cybersecurity work, including finding vulnerabilities, assessing risk, and developing patches. Google reports more reliable multi-step planning, fewer unsupported claims, and better handling of ambiguous requirements; these are reported claims, not independently established results. The text shows use through the AI SDK and says Claude Code, Codex, Cursor, and other agents can be configured by installing the latest Vercel CLI, running `npx vercel ai-gateway setup`, and selecting the model. AI Gateway offers usage and cost tracking, retries, failover, performance optimizations, reporting, Zero Data Retention support, API key budgets, and routing rules. It says pricing follows providers without markup or an inference platform fee, including BYOK requests.

### Source excerpt

Gemini 4 Carbon from Google is now available on AI Gateway. It is available at 50% off through November 30, 2026: Gemini 4 Carbon is built for complex software engineering, sustained agentic work, and cybersecurity defense. It has a 1M-token context window for working with large codebases and long inputs. On engineering tasks, Carbon carries demanding work through multiple stages, with improvements in coding, full-stack web development, and scientific reasoning. Its cybersecurity capabilities span finding vulnerabilities, validating their risk, and developing patches. Google also reports more reliable execution of multi-step plans, fewer unsupported claims, and better collaboration when requirements are ambiguous, helping agents follow through while respecting project constraints. Use google/gemini-4-carbon as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select google/gemini-4-carbon in the agent. See the coding agents guide for details. Try Gemini 4 Carbon in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Muse Ember now available on AI Gateway

DevFeed: [Muse Ember now available on AI Gateway](<https://devfeed.tech/articles/muse-ember-now-available-on-ai-gateway-123933.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/muse-ember-now-available-on-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-11-09T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [context window](<https://devfeed.tech/topics/context-window.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [apis](<https://devfeed.tech/tags/apis.md>), [bring-your-own-key](<https://devfeed.tech/tags/bring-your-own-key.md>), [built-in](<https://devfeed.tech/tags/built-in.md>), [byok](<https://devfeed.tech/tags/byok.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [data](<https://devfeed.tech/tags/data.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [effort](<https://devfeed.tech/tags/effort.md>), [muse-ember](<https://devfeed.tech/tags/muse-ember.md>)

### AI overview

Meta's Muse Ember is available through AI Gateway for repeated, bounded agent tasks such as coding subtasks, tool calls, and document summaries. It accepts text, images, and video with a 1M-token context window, supports tool calling, and offers adjustable reasoning effort from minimal to max. Access it through the AI SDK, Chat Completions, Responses, Anthropic Messages, or a connected coding agent; for agents such as Claude Code, Codex, and Cursor, the source says to run `npx vercel ai-gateway setup` and select `meta/muse-ember`. AI Gateway provides usage and cost tracking, retries, failover, routing, and reporting, and states that it passes through provider pricing without markup or an inference platform fee, including for BYOK.

### Source excerpt

Muse Ember from Meta is now available on AI Gateway. It is a lightweight reasoning model for the high-volume parts of an agent run, such as coding sub-tasks, tool calls, and document analysis. Muse Ember handles the bounded tasks agents repeat many times in a single run, like implementing a helper function, calling a tool, or summarizing a document. The model accepts text, image, and video input with a 1M-token context window, so an agent can pass it code, screenshots, documents, and clips in the same run. Tool calling lets your application feed each result into the next step. Reasoning effort is adjustable from minimal to max. Call it through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. Use meta/muse-ember as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select meta/muse-ember in the agent. See the coding agents guide for details. Try Muse Ember in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Give your Vercel AI SDK agents memory with Redis Agent Memory

DevFeed: [Give your Vercel AI SDK agents memory with Redis Agent Memory](<https://devfeed.tech/articles/give-your-vercel-ai-sdk-agents-memory-with-redis-agent-memory-125804.md>)

Original publisher: [Read original article](<https://redis.io/blog/give-your-vercel-ai-sdk-agents-memory-with-redis-agent-memory/>)

Author: Itamar Haber

Published: 2026-11-09T00:00:00Z

Content type: release

Language: en

Sources: [Redis Blog](<https://devfeed.tech/sources/redis-blog.md>), [Redis Blog](<https://devfeed.tech/sources/redis-blog-2.md>)

Topics: [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Redis](<https://devfeed.tech/topics/redis.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>)

Tags: [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [engineering-ai](<https://devfeed.tech/tags/engineering-ai.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [redis](<https://devfeed.tech/tags/redis.md>), [tech](<https://devfeed.tech/tags/tech.md>), [vercel-ai-sdk](<https://devfeed.tech/tags/vercel-ai-sdk.md>)

### AI overview

`@redis/vercel-ai-sdk` adds managed short-term session memory and long-term user memories to Vercel AI SDK agents through Redis Agent Memory. Its automatic-memory wrapper restores session context and recalls user memories before a model call, then records the user message and successful assistant steps. Alternatively, `memory.tools()` lets the model search, save, update, or forget memories, with optional lifecycle hooks for session recording. The two modes can coexist, but automatic recording and session-write tools on the same interaction may duplicate events. The server-side, ESM-only package requires Node.js 22+, AI SDK 7.x, Zod 4.x, and a provisioned Redis Cloud store. Context and read/write time are bounded, memory failures do not replace successful replies, and recording is best-effort because writes lack an idempotency key.

### Source excerpt

We've released @redis/vercel-ai-sdk, an open-source package that adds Redis Agent Memory to agents built with Vercel's AI SDK. Most agents start every conversation cold. Users repeat their preferences, and yesterday's context is gone. You can bolt on...

## Claude Fable 5.2 now available on AI Gateway

DevFeed: [Claude Fable 5.2 now available on AI Gateway](<https://devfeed.tech/articles/claude-fable-5-2-now-available-on-ai-gateway-123932.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/claude-fable-5-2-now-available-on-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-11-09T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [biology](<https://devfeed.tech/tags/biology.md>), [classifiers](<https://devfeed.tech/tags/classifiers.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [claude-fable](<https://devfeed.tech/tags/claude-fable.md>), [claude-fable-5-2](<https://devfeed.tech/tags/claude-fable-5-2.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [effort](<https://devfeed.tech/tags/effort.md>), [error](<https://devfeed.tech/tags/error.md>)

### AI overview

Anthropic's Claude Fable 5.2 is available through AI Gateway for open-ended technical work, with stated improvements in coding, reasoning, and vision over earlier Fable models. The text says it can handle long, ambiguous tasks unattended, delegate simpler work to smaller models, or advise other Claude models. Reasoning effort ranges from low to max, with high as the API default. Cybersecurity and biology classifiers are enabled. Access requires data retention: prompts and completions are retained for 30 days and not used to train Claude; requests are rejected if Zero Data Retention is enabled. To handle requests declined by the cybersecurity classifier, configure a `models` array in `providerOptions.gateway`; AI Gateway tries the listed models in order, as in the example using Opus 5.5 followed by Sonnet 5.5. The model is available via the AI SDK, Chat Completions, Responses, Anthropic Messages, and coding agents connected through AI Gateway.

### Source excerpt

Claude Fable 5.2 from Anthropic is now available on AI Gateway. Fable 5.2 is built for open-ended technical work and improves on earlier Fable models in coding, reasoning, and vision. It can run long, ambiguous tasks unattended, and works as an orchestrator that hands simpler tasks to smaller models, or as an advisor that other Claude models consult on harder problems. It also communicates more clearly and generates output faster than earlier Fable models. Effort runs from low to max, with high as the API default. Fable 5.2 has cybersecurity and biology safety classifiers enabled. Access to Claude Fable 5.2 requires data retention. Anthropic does not support Zero Data Retention for the model. Prompts and completions are retained for 30 days and are not used to train Claude. If your team has ZDR turned on, AI Gateway returns an error instead of sending the request to Fable 5.2. To keep requests served when a classifier is triggered, use model fallbacks. Add a models array to providerOptions.gateway, and AI Gateway tries each model in order when the cybersecurity classifier declines a request. Call it through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. Use anthropic/claude-fable-5.2 as the model name: This request falls back to Opus 5.5, then Sonnet 5.5, if the cybersecurity classifier declines it. The models option works the same way on every AI Gateway API format. To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Try Claude Fable 5.2 in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, inclu

## Gemini Omni 1.2 Flash now available on AI Gateway

DevFeed: [Gemini Omni 1.2 Flash now available on AI Gateway](<https://devfeed.tech/articles/gemini-omni-1-2-flash-now-available-on-ai-gateway-119784.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/gemini-omni-1-2-flash-now-available-on-ai-gateway>)

Author: Zachary Chen

Published: 2026-11-05T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Generative AI](<https://devfeed.tech/topics/generative-ai.md>), [generative-ai-tools](<https://devfeed.tech/topics/generative-ai-tools.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [audio](<https://devfeed.tech/tags/audio.md>), [edits](<https://devfeed.tech/tags/edits.md>), [extend](<https://devfeed.tech/tags/extend.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-omni](<https://devfeed.tech/tags/gemini-omni.md>), [gemini-omni-1-2-flash](<https://devfeed.tech/tags/gemini-omni-1-2-flash.md>), [google](<https://devfeed.tech/tags/google.md>), [model](<https://devfeed.tech/tags/model.md>), [name](<https://devfeed.tech/tags/name.md>), [native](<https://devfeed.tech/tags/native.md>), [reference](<https://devfeed.tech/tags/reference.md>), [sdk](<https://devfeed.tech/tags/sdk.md>), [source](<https://devfeed.tech/tags/source.md>), [text](<https://devfeed.tech/tags/text.md>), [up](<https://devfeed.tech/tags/up.md>), [video](<https://devfeed.tech/tags/video.md>), [videos](<https://devfeed.tech/tags/videos.md>)

### AI overview

Google's Gemini Omni 1.2 Flash is available through AI Gateway using one API key, without a separate Google account. It generates 3-15 second videos with native audio, edits clips of the same duration using up to six reference images, and supports extensions of 3-10 seconds per call up to 30 seconds total. Follow-up refinement uses `previousInteractionId`. Output options are 360p, 720p, 1080p, or 4K in 16:9 or 9:16. The excerpt shows `generateText` saving the returned MP4 file and `streamText` handling it through `fullStream` once delivered as a completed file. AI Gateway also offers usage and cost tracking, retries, failover, routing, and reporting; it states that inference follows provider pricing with no markup or platform fee, including BYOK requests.

### Source excerpt

Gemini Omni 1.2 Flash from Google is now available on AI Gateway. Generate videos from text prompts with one API key and no separate Google account. Gemini Omni 1.2 Flash generates 3-15 second videos with native audio and edits 3-15 second source clips with up to six reference images. Extend videos by 3-10 seconds per call, up to 30 seconds total, or refine generated clips in follow-up calls using previousInteractionId. Output supports 360p, 720p, 1080p, and 4K in 16:9 or 9:16. Use generateText or streamText in AI SDK to receive the generated video as a file. Generate a video Use google/gemini-omni-1.2-flash as the model name. This example generates a three-second, 360p clip and saves it as video.mp4: Receive video in a streaming response With streamText, read fullStream to handle generated files as they arrive. The video is delivered as a completed file: AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. Explore more models in the AI Gateway model catalog. Read more

## Kimi K3.1 Pro now has more ZDR providers on AI Gateway

DevFeed: [Kimi K3.1 Pro now has more ZDR providers on AI Gateway](<https://devfeed.tech/articles/kimi-k3-1-pro-now-has-more-zdr-providers-on-ai-gateway-117141.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/kimi-k3-1-pro-now-has-more-zdr-providers-on-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-11-04T17:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [3d-modeling](<https://devfeed.tech/tags/3d-modeling.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [failover](<https://devfeed.tech/tags/failover.md>), [financial](<https://devfeed.tech/tags/financial.md>), [image](<https://devfeed.tech/tags/image.md>), [input](<https://devfeed.tech/tags/input.md>), [install](<https://devfeed.tech/tags/install.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [k3](<https://devfeed.tech/tags/k3.md>), [kimi](<https://devfeed.tech/tags/kimi.md>), [kimi-k3-1-pro](<https://devfeed.tech/tags/kimi-k3-1-pro.md>), [providers](<https://devfeed.tech/tags/providers.md>)

### AI overview

Kimi K3.1 Pro and K3.1 Pro Highspeed are available through AI Gateway from additional ZDR providers; Moonshot AI had previously been the only provider serving them. Both models accept image input and have a 1M-token context window. The text highlights coding, 3D modeling, and financial analysis, and says Highspeed is suited to interactive work where response time matters. They can be called through the AI SDK, Chat Completions, Responses, Anthropic Messages, or connected coding agents. ZDR can be required per request with the gateway provider option or for all team requests through dashboard settings. When enabled, routing is limited to providers with a ZDR agreement, and requests fail if none is available for the model.

### Source excerpt

Kimi K3.1 Pro and its higher-speed version, Kimi K3.1 Pro Highspeed, are now available on AI Gateway from more Zero Data Retention (ZDR) providers. Until today, Moonshot AI was the only provider serving either model. K3.1 Pro improves on earlier Kimi models in coding, 3D modeling, and financial analysis, and can carry long agent runs from a small fix to a full project. Both models have a 1M-token context window and accept image input, and Highspeed suits interactive work like coding agents, where response time matters. Call either model through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. For Highspeed, use moonshotai/kimi-k3.1-pro-highspeed in place of the model name below. Use moonshotai/kimi-k3.1-pro as the model name: Setting zeroDataRetention in the gateway provider options requires ZDR for that request. To require it for every request your team sends, including requests from coding agents, turn on ZDR in the AI Gateway dashboard settings. With either one on, AI Gateway routes only to providers with a ZDR agreement. If none is available for the model, the request fails instead of going to a provider without one. To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select moonshotai/kimi-k3.1-pro or moonshotai/kimi-k3.1-pro-highspeed in the agent. See the coding agents guide for details. Try Kimi K3.1 Pro in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Virtual models now available on AI Gateway

DevFeed: [Virtual models now available on AI Gateway](<https://devfeed.tech/articles/virtual-models-now-available-on-ai-gateway-105571.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/virtual-models-now-available-on-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-10-28T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [api](<https://devfeed.tech/tags/api.md>), [apps](<https://devfeed.tech/tags/apps.md>), [caching](<https://devfeed.tech/tags/caching.md>), [cli](<https://devfeed.tech/tags/cli.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [configure](<https://devfeed.tech/tags/configure.md>), [control](<https://devfeed.tech/tags/control.md>), [custom](<https://devfeed.tech/tags/custom.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [effort](<https://devfeed.tech/tags/effort.md>), [examples](<https://devfeed.tech/tags/examples.md>), [models](<https://devfeed.tech/tags/models.md>)

### AI overview

AI Gateway virtual models let apps and agents use a custom ID such as `vmc/coding-agent` for a centrally managed model and settings configuration, which can be changed without redeploying or reconfiguring clients. They can set coding-agent options, choose providers and fallbacks, enforce requirements such as Zero Data Retention, and attach reporting tags. Create one in the Virtual Models page or with the Vercel CLI by setting a slug, underlying model, and configuration. Use it by replacing the provider model ID in compatible requests, or selecting it in a coding agent's configuration. The excerpt says virtual models work with every model type on AI Gateway.

### Source excerpt

Virtual models are now available on AI Gateway. A virtual model is a saved configuration that tells AI Gateway which model and settings to use. Your apps and agents call it with a custom model ID, such as vmc/coding-agent. You can change the model or settings centrally in AI Gateway without redeploying your apps or reconfiguring your agents. Use virtual models to: Configure coding agents: Set reasoning effort, fast mode, prompt caching, and other options even when your agent doesn't expose them. Control routing and compliance: Choose providers, configure fallback models, and enforce requirements such as Zero Data Retention. Attribute spend: Attach custom reporting tags to every request that uses the virtual model. To create a virtual model, open the Virtual Models page and click Create Virtual Model. Enter a slug, choose the underlying model, configure the settings you want requests to use, and save. Or create one with the Vercel CLI: To use a virtual model, replace the provider model ID in your AI SDK or compatible API requests with vmc/<slug>, such as vmc/coding-agent. For coding agents, connect to AI Gateway with vercel ai-gateway setup if needed, then select your virtual model in the agent's model picker or configuration. Virtual models work with every model type on AI Gateway. Read the launch post for examples or learn more in the virtual models documentation. Read more

## Particle-1 is now available on AI Gateway

DevFeed: [Particle-1 is now available on AI Gateway](<https://devfeed.tech/articles/particle-1-is-now-available-on-ai-gateway-105507.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/particle-1-is-now-available-on-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-10-28T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [gateway](<https://devfeed.tech/topics/gateway.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [post-training](<https://devfeed.tech/topics/post-training.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [api](<https://devfeed.tech/tags/api.md>), [api-key](<https://devfeed.tech/tags/api-key.md>), [coding](<https://devfeed.tech/tags/coding.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [deepseek-v4-1-flash](<https://devfeed.tech/tags/deepseek-v4-1-flash.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [environment](<https://devfeed.tech/tags/environment.md>), [failover](<https://devfeed.tech/tags/failover.md>), [fewer](<https://devfeed.tech/tags/fewer.md>), [inference](<https://devfeed.tech/tags/inference.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [performance](<https://devfeed.tech/tags/performance.md>), [planning](<https://devfeed.tech/tags/planning.md>), [playground](<https://devfeed.tech/tags/playground.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [reasoning](<https://devfeed.tech/tags/reasoning.md>)

### AI overview

Particle-1 is available on AI Gateway for software engineering tasks, with a 1M-token context window. Particle AI says it is post-trained on DeepSeek V4.1 Flash and aims to use fewer tokens through shorter reasoning, fewer trial-and-repair rounds, and more focused exploration. The text suggests it for debugging, planning code changes, and multi-step engineering problems. To call it, set `AI_GATEWAY_API_KEY` and use `particle/particle-1`; coding agents such as Claude Code, Codex, and Cursor can be configured with `npx vercel ai-gateway setup`. AI Gateway offers usage and cost tracking, retries, failover, routing rules, reporting, Zero Data Retention support, and API-key budgets. It says pricing reflects provider rates with no markup or platform fee on inference, including BYOK requests.

### Source excerpt

Particle-1 from Particle AI is now available on AI Gateway. It is post-trained on DeepSeek V4.1 Flash, with a focus on completing software engineering tasks using fewer tokens. Particle describes the gains as shorter reasoning, fewer rounds of trial and repair, and more focused exploration. Use it for debugging, planning code changes, and breaking down multi-step engineering problems. Particle-1 has a 1M-token context window for working with code and extended task histories. Set AI_GATEWAY_API_KEY in your environment. Use particle/particle-1 as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest version of Vercel CLI and run setup: Then select particle/particle-1 in the agent. See the coding agents guide for details. Try Particle-1 in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## GPT-6.1 Terra now available on AI Gateway

DevFeed: [GPT-6.1 Terra now available on AI Gateway](<https://devfeed.tech/articles/gpt-6-1-terra-now-available-on-ai-gateway-100784.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/gpt-6-1-terra-now-available-on-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-10-26T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [OpenAI](<https://devfeed.tech/topics/openai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [litellm](<https://devfeed.tech/topics/litellm.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [codex](<https://devfeed.tech/topics/codex.md>), [cursor](<https://devfeed.tech/topics/cursor.md>)

Tags: [accounting](<https://devfeed.tech/tags/accounting.md>), [accounting-software](<https://devfeed.tech/tags/accounting-software.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [api](<https://devfeed.tech/tags/api.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [bring-your-own-key](<https://devfeed.tech/tags/bring-your-own-key.md>), [caching](<https://devfeed.tech/tags/caching.md>), [chat](<https://devfeed.tech/tags/chat.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coding-tasks](<https://devfeed.tech/tags/coding-tasks.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-6-1](<https://devfeed.tech/tags/gpt-6-1.md>), [gpt-6-1-terra](<https://devfeed.tech/tags/gpt-6-1-terra.md>)

### AI overview

OpenAI's GPT-6.1 Terra is available through AI Gateway for visual reasoning, computer use, writing, and high-volume document or desktop workflows. The text says it improves on the previous Terra model in visual reasoning, factual accuracy, and coding, but recommends larger GPT-6 models for the most complex coding tasks. It accepts text and images, returns text, and has a context window exceeding 1M tokens; supported features include configurable reasoning effort, structured outputs, tool calling, and prompt caching. Latency-sensitive use can select `openai/gpt-6.1-terra-fast`. Integration options include the AI SDK, Chat Completions API, Responses API, and connected coding agents. For Codex, Cursor, and others, the text instructs users to run `npx vercel ai-gateway setup` and select `openai/gpt-6.1-terra`. AI Gateway offers usage and cost tracking, retries, failover, routing, reporting, Zero Data Retention support, and API-key budgets. It says pricing matches providers with no markup or platform inference fee, including BYOK requests.

### Source excerpt

GPT-6.1 Terra from OpenAI is now available on AI Gateway. GPT-6.1 Terra is a fast model for visual reasoning, computer use, and writing, and it improves on the previous Terra model in visual reasoning, factual accuracy, and coding. It suits high-volume work in documents and desktop apps, such as filling out forms, interpreting technical drawings, or entering invoice details into accounting software. OpenAI still recommends its larger GPT-6 models for the most complex coding tasks. The model accepts text and images and returns text, with a context window of more than 1M tokens. It supports configurable reasoning effort, structured outputs, tool calling, and implicit and explicit prompt caching. For latency-sensitive work, fast mode is available as openai/gpt-6.1-terra-fast. GPT-6.1 Terra works with the AI SDK, the OpenAI-compatible Chat Completions API, the Responses API, and coding agents connected to AI Gateway. Use openai/gpt-6.1-terra as the model name: To use it in Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select openai/gpt-6.1-terra in the agent. See the coding agents guide for details. Try GPT-6.1 Terra in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are available now in AI Gateway

DevFeed: [Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are available now in AI Gateway](<https://devfeed.tech/articles/kimi-k3-1-pro-and-kimi-k3-1-pro-highspeed-are-available-now-in-ai-gateway-98347.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/kimi-k3-1-pro-and-kimi-k3-1-pro-highspeed-are-available-now-in-ai-gateway>)

Author: Jerilyn Zheng

Published: 2026-10-23T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Finance](<https://devfeed.tech/topics/finance.md>)

Tags: [3d](<https://devfeed.tech/tags/3d.md>), [3d-modeling](<https://devfeed.tech/tags/3d-modeling.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-tasks](<https://devfeed.tech/tags/agentic-tasks.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [animation](<https://devfeed.tech/tags/animation.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [api-keys](<https://devfeed.tech/tags/api-keys.md>), [apis](<https://devfeed.tech/tags/apis.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [k3](<https://devfeed.tech/tags/k3.md>), [kimi](<https://devfeed.tech/tags/kimi.md>), [kimi-k3](<https://devfeed.tech/tags/kimi-k3.md>), [kimi-k3-1-pro](<https://devfeed.tech/tags/kimi-k3-1-pro.md>)

### AI overview

Moonshot AI's Kimi K3.1 Pro and faster Highspeed variant are available through AI Gateway. The excerpt says K3.1 Pro improves coding, 3D modeling, financial analysis, and agentic tasks over Kimi K3, while retaining a 1M-token context window and image input. It describes coding work from codebase fixes to full projects and long agent runs, plus linked financial models and research grounded in source documents. Both variants can be called through the AI SDK, Chat Completions, Responses, Anthropic Messages, or supported coding agents; the excerpt gives `npx vercel ai-gateway setup` for configuring agents and distinct model names for each variant. AI Gateway offers usage and cost tracking, retries, failover, routing, reporting, Zero Data Retention support, and API-key budgets. It states that pricing matches providers without markup or an inference platform fee, including BYOK. Broader provider support is expected after Moonshot's planned model-weight release by November 4.

### Source excerpt

Kimi K3.1 Pro from Moonshot AI is now available on AI Gateway, along with Kimi K3.1 Pro Highspeed, a faster version for interactive use. K3.1 Pro is the first model in Moonshot's K3.1 series. It builds on Kimi K3 with improvements in coding, 3D modeling, financial analysis, and agentic tasks, and keeps the 1M-token context window and image input. For coding, K3.1 Pro handles work ranging from small fixes in an existing codebase to building a full project, including long agent runs with many steps. It builds front-end pages and interactive scenes with stronger typography and animation than earlier Kimi models. In finance, it can carry a task from start to finish, such as building a linked financial model with adjustable assumptions and scenarios, or writing research grounded in source documents. K3.1 Pro makes fewer factual errors than earlier Kimi models on difficult prompts. Moonshot AI plans to release the model weights by November 4: support for more providers will follow. Call either model through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. For Highspeed, use moonshotai/kimi-k3.1-pro-highspeed in place of the model name below. Use moonshotai/kimi-k3.1-pro as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select moonshotai/kimi-k3.1-pro or moonshotai/kimi-k3.1-pro-highspeed in the agent. See the coding agents guide for details. Try Kimi K3.1 Pro in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all la

## DeepSeek V4.1 Flash is now available in Token Pass

DevFeed: [DeepSeek V4.1 Flash is now available in Token Pass](<https://devfeed.tech/articles/deepseek-v4-1-flash-is-now-available-in-token-pass-91279.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/deepseek-v4-1-flash-is-now-available-in-token-pass>)

Author: Krish Krish

Published: 2026-10-20T00:01:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Language models](<https://devfeed.tech/topics/language-models.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [cline](<https://devfeed.tech/tags/cline.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [dashboard](<https://devfeed.tech/tags/dashboard.md>), [data](<https://devfeed.tech/tags/data.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [deepseek](<https://devfeed.tech/tags/deepseek.md>), [deepseek-v4-1-flash](<https://devfeed.tech/tags/deepseek-v4-1-flash.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [flash](<https://devfeed.tech/tags/flash.md>), [fx](<https://devfeed.tech/tags/fx.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [glm](<https://devfeed.tech/tags/glm.md>), [pass](<https://devfeed.tech/tags/pass.md>), [token](<https://devfeed.tech/tags/token.md>)

### AI overview

Token Pass now offers DeepSeek V4.1 Flash using weights 1017, alongside Kimi K3 and GLM 5.3; each is accessed through its preferred provider. On Pro teams, Token Pass costs $30 per month and grants $80 in monthly credit through AI Gateway. It can be used with coding agents such as fx, Pi, Cline, and Command Code, or with a custom build using the AI SDK. Zero Data Retention is enabled by default. Add the model from the Token Pass page in the team's AI Gateway dashboard; setup documentation is also available.

### Source excerpt

Token Pass now includes DeepSeek V4.1 Flash, alongside Kimi K3 and GLM 5.3, each accessed through its preferred provider, with more models to come. The DeepSeek model uses the latest weights (1017). Token Pass is a $30/month subscription on Pro teams that grants $80 in monthly credit and runs through AI Gateway. Use it with any coding agent such as fx, Pi, Cline, Command Code etc. or build your own with the AI SDK, with Zero Data Retention enabled by default. Add DeepSeek V4.1 Flash from the Token Pass page in your team's AI Gateway dashboard, or read the Token Pass documentation for setup. Read more

## LLM Structured Output with JSON Schema: Typed Responses in TypeScript

DevFeed: [LLM Structured Output with JSON Schema: Typed Responses in TypeScript](<https://devfeed.tech/articles/llm-structured-output-with-json-schema-typed-responses-in-typescript-90075.md>)

Original publisher: [Read original article](<https://www.sitepoint.com/llm-structured-output-json-schema/>)

Author: SitePoint Team

Published: 2026-10-19T15:41:23Z

Content type: tutorial

Language: en

Sources: [SitePoint](<https://devfeed.tech/sources/sitepoint.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [JSON Schema](<https://devfeed.tech/topics/json-schema.md>), [TypeScript](<https://devfeed.tech/topics/typescript.md>), [function calling](<https://devfeed.tech/topics/function-calling.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [AI Prompt Templates](<https://devfeed.tech/topics/ai-prompt-templates.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [anthropic-ai](<https://devfeed.tech/tags/anthropic-ai.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [app](<https://devfeed.tech/tags/app.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [azure-openai](<https://devfeed.tech/tags/azure-openai.md>), [claude](<https://devfeed.tech/tags/claude.md>), [function-calling](<https://devfeed.tech/tags/function-calling.md>), [json](<https://devfeed.tech/tags/json.md>), [json-schema](<https://devfeed.tech/tags/json-schema.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llms](<https://devfeed.tech/tags/llms.md>), [programming](<https://devfeed.tech/tags/programming.md>), [retries](<https://devfeed.tech/tags/retries.md>), [schema](<https://devfeed.tech/tags/schema.md>), [structured-output](<https://devfeed.tech/tags/structured-output.md>), [typescript](<https://devfeed.tech/tags/typescript.md>), [validation](<https://devfeed.tech/tags/validation.md>), [zod](<https://devfeed.tech/tags/zod.md>)

### AI overview

This tutorial shows how to produce and validate structured LLM output across OpenAI, Gemini, Anthropic, vLLM, and Azure OpenAI. It demonstrates JSON Schema constraints, TypeScript schemas with Zod, function calling, and a provider-agnostic validation wrapper that retries failed responses a bounded number of times. It also discusses provider differences, schema limitations, and practices such as keeping schemas shallow and checking schema changes against each provider.

### Source excerpt

Get reliable, typed JSON from LLMs using schema-constrained outputs, function calling, and a TypeScript Zod validation layer with bounded retries. Continue reading LLM Structured Output with JSON Schema: Typed Responses in TypeScript on SitePoint.

## Structured Output with TanStack AI

DevFeed: [Structured Output with TanStack AI](<https://devfeed.tech/articles/structured-output-with-tanstack-ai-90086.md>)

Original publisher: [Read original article](<https://blog.master.dev/structured-output-with-tanstack-ai/>)

Author: Adam Rackis

Published: 2026-10-19T12:25:32Z

Content type: tutorial

Language: en

Sources: [Master.dev Blog RSS Feed](<https://devfeed.tech/sources/master-dev-blog-rss-feed.md>)

Topics: [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [JSON](<https://devfeed.tech/topics/json.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [a2ui](<https://devfeed.tech/topics/a2ui.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [anthropic-claude](<https://devfeed.tech/tags/anthropic-claude.md>), [api](<https://devfeed.tech/tags/api.md>), [blog-post](<https://devfeed.tech/tags/blog-post.md>), [claude-opus](<https://devfeed.tech/tags/claude-opus.md>), [claude-opus-5](<https://devfeed.tech/tags/claude-opus-5.md>), [code](<https://devfeed.tech/tags/code.md>), [front-end](<https://devfeed.tech/tags/front-end.md>), [streaming](<https://devfeed.tech/tags/streaming.md>), [structured-output](<https://devfeed.tech/tags/structured-output.md>), [tanstack](<https://devfeed.tech/tags/tanstack.md>), [typescript](<https://devfeed.tech/tags/typescript.md>), [zod](<https://devfeed.tech/tags/zod.md>)

### AI overview

This tutorial shows how to use TanStack AI to constrain model responses with a Zod schema, render structured workout data, and stream partial JSON payloads. It explains handling incomplete values with deeply optional types and components that check which properties are available.

### Source excerpt

Part 2 of this intro to TanStack AI covers structured output: constraining the model's response to a Zod schema, then streaming that JSON in and rendering it while it's still incomplete.

## MiniMax M3.1 Flash now available on AI Gateway for free

DevFeed: [MiniMax M3.1 Flash now available on AI Gateway for free](<https://devfeed.tech/articles/minimax-m3-1-flash-now-available-on-ai-gateway-for-free-89978.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/minimax-m3-1-flash-now-available-on-ai-gateway-for-free>)

Author: Jerilyn Zheng

Published: 2026-10-19T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Tool](<https://devfeed.tech/topics/tool.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>)

Tags: [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [minimax](<https://devfeed.tech/tags/minimax.md>)

### AI overview

MiniMax M3.1 Flash is available through Vercel AI Gateway for free until Oct 22 when MiniMax serves the request. The open-weight multimodal model supports coding and agentic work with a 1M-token context window. The announcement provides SDK usage and coding-agent setup instructions, and explains that pinned requests switch to MiniMax's standard rate after the offer ends.

### Source excerpt

MiniMax M3.1 Flash from MiniMax is now available on AI Gateway for free until Oct 22. MiniMax M3.1 Flash is an open-weight multimodal model for coding and agentic work, with a 1M-token context window for long documents and multi-step agent sessions. Compared with earlier MiniMax models, M3.1 Flash improves on complex agentic tasks, coding, and cybersecurity. On the agent side, that covers multi-step business processes and computer use that carries a task from one application to the next. For coding, MiniMax reports its best results on application development, particularly frontend interactions, targeted bug fixes, and component tests. The free rate applies only when MiniMax serves the request. To make sure it does, sort the provider with order in the gateway provider options. After the offer ends, pinned requests bill at MiniMax's standard rate. Call it through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. Use minimax/minimax-m3.1-flash as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select minimax/minimax-m3.1-flash in the agent. See the coding agents guide for details. Try MiniMax M3.1 Flash in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Mercury 3 now available on AI Gateway

DevFeed: [Mercury 3 now available on AI Gateway](<https://devfeed.tech/articles/mercury-3-now-available-on-ai-gateway-90423.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/mercury-3-now-available-on-ai-gateway>)

Author: Zachary Chen

Published: 2026-10-19T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [api](<https://devfeed.tech/tags/api.md>), [bring-your-own-key](<https://devfeed.tech/tags/bring-your-own-key.md>), [failover](<https://devfeed.tech/tags/failover.md>), [latency](<https://devfeed.tech/tags/latency.md>), [models](<https://devfeed.tech/tags/models.md>), [performance](<https://devfeed.tech/tags/performance.md>), [retention](<https://devfeed.tech/tags/retention.md>), [retries](<https://devfeed.tech/tags/retries.md>), [routing](<https://devfeed.tech/tags/routing.md>)

### AI overview

Vercel announced that Inception's Mercury 3 is available through AI Gateway, reporting benchmark generation speeds above 1,000 tokens per second and a 1M-token context window. The release describes diffusion-based parallel text refinement and example workloads, and explains how developers can call the model through the AI SDK or coding agents. AI Gateway also supports usage and cost tracking, retries, failover, routing, and performance settings.

### Source excerpt

Mercury 3 from Inception is now available on AI Gateway with 50% off launch pricing. Inception reports strong results across a range of benchmarks, with generation speeds above 1,000 tokens per second. Mercury 3 uses diffusion to generate text through parallel refinement. It brings improved reasoning to latency-sensitive workloads such as browser agents, real-time search, interactive education, and customer support. A 1M-token context window gives those applications room for long documents and extended conversation histories. Set AI_GATEWAY_API_KEY in your environment. Use inception/mercury-3 as the model name: To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select inception/mercury-3 in the agent. See the coding agents guide for details. Try Mercury 3 in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Reflection AI's Beam now available on AI Gateway for free

DevFeed: [Reflection AI's Beam now available on AI Gateway for free](<https://devfeed.tech/articles/reflection-ai-s-beam-now-available-on-ai-gateway-for-free-88884.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/reflection-ai-beam-now-available-on-ai-gateway-for-free>)

Author: Zachary Chen

Published: 2026-10-16T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [api](<https://devfeed.tech/tags/api.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [failover](<https://devfeed.tech/tags/failover.md>), [free](<https://devfeed.tech/tags/free.md>), [guide](<https://devfeed.tech/tags/guide.md>), [inference](<https://devfeed.tech/tags/inference.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [provides](<https://devfeed.tech/tags/provides.md>), [reflection-ai](<https://devfeed.tech/tags/reflection-ai.md>), [retries](<https://devfeed.tech/tags/retries.md>), [routing](<https://devfeed.tech/tags/routing.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

Reflection AI's Beam reasoning model is available through Vercel AI Gateway for a limited-time free launch period. The release describes its coding and agentic task support, tool calling, structured outputs, adjustable reasoning effort, and 1M-token context window. It also explains two model names with different behavior after the free offer ends and shows setup for coding agents.

### Source excerpt

Beam from Reflection AI, previously available in stealth as stealth/cat-jam, is now available on AI Gateway. Beam is free to use for a limited time during the launch period when serviced by Reflection AI. Beam is an low latency US open-weight reasoning model for coding and agentic tasks, with weights released under Apache 2.0. Beam supports tool calling and structured outputs, with a 1M-token context window for code, documents, and conversation history. Reasoning effort is adjustable. Beam is designed for speed, activating only 23B of its 501B parameters per token and avoiding tokens a task doesn't need, so it tends to reach answers sooner than larger open models. There are 2 ways to access Beam for free: Using the standard model name (reflection/beam with provider reflection). When the free period ends, the model slug will automatically transfer over to pricing with no downtime. Using the -free suffix to the standard name (reflection/beam-free). The model will stop serving when the free offer ends. To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select reflection/beam or reflection/beam-free in the agent. See the coding agents guide for details. Try Beam in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. Read more

## Introducing Token Pass

DevFeed: [Introducing Token Pass](<https://devfeed.tech/articles/introducing-token-pass-88224.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/introducing-token-pass>)

Author: Jeff Pope

Published: 2026-10-15T07:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Secure token management](<https://devfeed.tech/topics/secure-token-management.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [inference-providers](<https://devfeed.tech/topics/inference-providers.md>)

Tags: [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [billing](<https://devfeed.tech/tags/billing.md>), [glm-5-3](<https://devfeed.tech/tags/glm-5-3.md>), [inference](<https://devfeed.tech/tags/inference.md>), [kimi-k3](<https://devfeed.tech/tags/kimi-k3.md>), [token](<https://devfeed.tech/tags/token.md>), [zero-data-retention](<https://devfeed.tech/tags/zero-data-retention.md>)

### AI overview

Vercel Token Pass enters early access for Pro teams at $30 per month, providing $80 in monthly credit for GLM 5.3 and Kimi K3 through AI Gateway. Teams can use it with coding agents or build a personal agent with the AI SDK. Zero Data Retention is enabled by default, and requests stop when the credit is exhausted without automatic overage charges.

### Source excerpt

Vercel Token Pass is now in early access for Pro teams. For $30 per month, your team gets $80 in monthly credit for GLM 5.3 and Kimi K3, with more models to come. Use Token Pass with coding agents such as fx, Command Code, and Pi, or build your own personal agent with the AI SDK. Token Pass runs through AI Gateway, so you can choose your tools and switch between included models using your team's shared credit. Token Pass has Zero Data Retention (ZDR) enabled by default. Requests run through selected providers with inference in the US and EU. AI Gateway and the provider delete your prompts and responses after each request, and your prompts aren't used to train models. To get started: Open the Token Pass page in your team's AI Gateway dashboard. Activate your subscription, create a Token Pass API key, and follow the setup instructions to connect your agent. Select GLM 5.3 or Kimi K3, and start building. The subscription renews monthly unless canceled. Unused credit doesn't roll over. When your credit runs out, Token Pass requests stop until the next billing period, with no automatic overage charges. Learn more in the Token Pass documentation. Read more

## Muse Spark Open now available on AI Gateway

DevFeed: [Muse Spark Open now available on AI Gateway](<https://devfeed.tech/articles/muse-spark-open-now-available-on-ai-gateway-88227.md>)

Original publisher: [Read original article](<https://vercel.com/changelog/muse-spark-open-now-available-on-ai-gateway>)

Author: Zachary Chen

Published: 2026-10-15T00:00:00Z

Content type: release

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [Advanced AI workflows](<https://devfeed.tech/topics/advanced-ai-workflows.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [Chat completions endpoints](<https://devfeed.tech/topics/chat-completions-endpoints.md>), [open-responses](<https://devfeed.tech/topics/open-responses.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-gateway](<https://devfeed.tech/tags/ai-gateway.md>), [ai-sdk](<https://devfeed.tech/tags/ai-sdk.md>), [api](<https://devfeed.tech/tags/api.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context](<https://devfeed.tech/tags/context.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [data-retention](<https://devfeed.tech/tags/data-retention.md>), [failover](<https://devfeed.tech/tags/failover.md>), [keys](<https://devfeed.tech/tags/keys.md>), [muse-spark](<https://devfeed.tech/tags/muse-spark.md>), [muse-spark-open](<https://devfeed.tech/tags/muse-spark-open.md>), [open](<https://devfeed.tech/tags/open.md>), [playground](<https://devfeed.tech/tags/playground.md>), [spark](<https://devfeed.tech/tags/spark.md>)

### AI overview

Vercel has added Meta's open-weight Muse Spark Open reasoning model to AI Gateway. The model targets coding and agentic workflows such as multi-file refactoring, debugging, and large-codebase analysis, with text and image input and a 1M-token context window. It is available through several API formats and coding agents, and AI Gateway provides usage and cost tracking, retries, failover, and related controls.

### Source excerpt

Muse Spark Open from Meta is now available on AI Gateway. The open-weight reasoning model is designed for coding and agentic workflows, including multi-file refactoring, debugging, and understanding large codebases. Muse Spark Open supports text and image input with a 1M-token context window, allowing agents to work with code and screenshots in the same request. It is available with ZDR and no training, without creating separate provider accounts. Use meta/muse-spark-open as the model name across all API formats and coding agents. The model is available across the AI SDK, the OpenAI-compatible Chat Completions and Responses APIs, the Anthropic-compatible Messages API, and coding agents connected to AI Gateway. To use it in Claude Code, Codex, Cursor, and more, install the latest Vercel CLI and run setup: Then select meta/muse-spark-open in the agent. See the coding agents guide for details. Try Muse Spark Open in the model playground. AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more. AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests. You can view all language models available on AI Gateway. Read more

## Announcing Day 0 Support for NVIDIA Nemotron 3.5 Super VL on vLLM

DevFeed: [Announcing Day 0 Support for NVIDIA Nemotron 3.5 Super VL on vLLM](<https://devfeed.tech/articles/announcing-day-0-support-for-nvidia-nemotron-3-5-super-vl-on-vllm-88077.md>)

Original publisher: [Read original article](<https://vllm.ai/blog/2026-10-15-nemotron-3-5-super-vl-vllm>)

Author: NVIDIA Nemotron Team

Published: 2026-10-15T00:00:00Z

Content type: release

Language: en

Sources: [vLLM Blog](<https://devfeed.tech/sources/vllm-blog.md>)

Topics: [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [vllm](<https://devfeed.tech/topics/vllm.md>), [tgi](<https://devfeed.tech/topics/tgi.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [NVFP4](<https://devfeed.tech/topics/nvfp4.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-workflows](<https://devfeed.tech/tags/agent-workflows.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [batching](<https://devfeed.tech/tags/batching.md>), [caching](<https://devfeed.tech/tags/caching.md>), [day-0-support](<https://devfeed.tech/tags/day-0-support.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [image](<https://devfeed.tech/tags/image.md>), [llm-inference](<https://devfeed.tech/tags/llm-inference.md>), [model-serving](<https://devfeed.tech/tags/model-serving.md>), [model-support](<https://devfeed.tech/tags/model-support.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nvidia-nemotron](<https://devfeed.tech/tags/nvidia-nemotron.md>), [open-source-ai](<https://devfeed.tech/tags/open-source-ai.md>), [token](<https://devfeed.tech/tags/token.md>), [video](<https://devfeed.tech/tags/video.md>), [vllm](<https://devfeed.tech/tags/vllm.md>), [vllm-blog](<https://devfeed.tech/tags/vllm-blog.md>)

### AI overview

NVIDIA announces support for Nemotron 3.5 Super VL in vLLM, describing a multimodal model for long-running agent workflows that can process text, images, documents, and video. The article explains serving options, including an OpenAI-compatible API, continuous batching, prefix caching, speculative decoding, and NVFP4 inference, and outlines customization with NVIDIA NeMo. It also reports performance comparisons for agentic tasks and points readers to model weights and a getting-started cookbook.

### Source excerpt

Run NVIDIA Nemotron 3.5 Super VL on vLLM for multimodal agent workflows with image, document, and video understanding, OpenAI-compatible serving, and multi-token prediction.

## How to Test Multi-Turn Conversations With Simulated Users

DevFeed: [How to Test Multi-Turn Conversations With Simulated Users](<https://devfeed.tech/articles/how-to-test-multi-turn-conversations-with-simulated-users-87107.md>)

Original publisher: [Read original article](<https://www.lyzr.ai/blog/test-multi-turn-conversations/>)

Author: Lyzr Team

Published: 2026-10-14T14:15:14Z

Content type: tutorial

Language: en

Sources: [Lyzr.ai](<https://devfeed.tech/sources/lyzr-ai.md>)

Topics: [Test automation](<https://devfeed.tech/topics/test-automation.md>), [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [how-to](<https://devfeed.tech/tags/how-to.md>)

### AI overview

This tutorial explains how to test AI agents across multi-turn conversations using simulated users with defined personas and checkable goals. It covers repeated scenario runs, checking system state and conversation quality, validating simulators against human conversations, and making test results a release gate.

### Source excerpt

Your billing support agent passed all 240 test cases last sprint. On Tuesday a customer writes: "I was charged twice for the roaming pack." The...

[Next page](<https://devfeed.tech/topics/vercel-ai-sdk.md?cursor=WyIyMDI2LTEwLTE0VDE0OjE1OjE0KzAwOjAwIiwgIjM3ODY0ZDM3LTdjMmUtNDZiZC05M2FmLTFkOTM4MmZkOTYzOSJd>)